Merge tag 'drm-msm-next-2021-08-12' of https://gitlab.freedesktop.org/drm/msm into drm-next

This is the main pull for v5.15, after the early pull request with
drm/scheduler conversion:

* New a6xx GPU support: a680 and 7c3
* dsi: 7nm phi, sc7280 support, test pattern generator support
* mdp4 fixes for older hw like the nexus7
* displayport fixes

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGs_tyanTeDGMH1X+Uf4wdyy7jYj-CinGXXVETiYOESahw@mail.gmail.com

47 files changed, 1193 insertions, 585 deletions

diff --git a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
index 76348b71f736..760eec6b0db1 100644
--- a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
+++ b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
@@ -64,6 +64,18 @@ properties:
       Indicates if the DSI controller is driving a panel which needs
       2 DSI links.
 
+  assigned-clocks:
+    minItems: 2
+    maxItems: 2
+    description: |
+      Parents of "byte" and "pixel" for the given platform.
+
+  assigned-clock-parents:
+    minItems: 2
+    maxItems: 2
+    description: |
+      The Byte clock and Pixel clock PLL outputs provided by a DSI PHY block.
+
   power-domains:
     maxItems: 1
 
@@ -119,6 +131,8 @@ required:
   - clock-names
   - phys
   - phy-names
+  - assigned-clocks
+  - assigned-clock-parents
   - power-domains
   - operating-points-v2
   - ports
@@ -159,6 +173,9 @@ examples:
            phys = <&dsi0_phy>;
            phy-names = "dsi";
 
+           assigned-clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK_SRC>, <&dispcc DISP_CC_MDSS_PCLK0_CLK_SRC>;
+           assigned-clock-parents = <&dsi_phy 0>, <&dsi_phy 1>;
+
            power-domains = <&rpmhpd SC7180_CX>;
            operating-points-v2 = <&dsi_opp_table>;
 
diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-7nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-7nm.yaml
new file mode 100644
index 000000000000..4265399bb154
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-7nm.yaml
@@ -0,0 +1,72 @@
+# SPDX-License-Identifier: GPL-2.0-only or BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/msm/dsi-phy-7nm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Display DSI 7nm PHY
+
+maintainers:
+  - Jonathan Marek <jonathan@marek.ca>
+
+allOf:
+  - $ref: dsi-phy-common.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - const: qcom,dsi-phy-7nm
+      - const: qcom,dsi-phy-7nm-8150
+      - const: qcom,sc7280-dsi-phy-7nm
+
+  reg:
+    items:
+      - description: dsi phy register set
+      - description: dsi phy lane register set
+      - description: dsi pll register set
+
+  reg-names:
+    items:
+      - const: dsi_phy
+      - const: dsi_phy_lane
+      - const: dsi_pll
+
+  vdds-supply:
+    description: |
+      Connected to VDD_A_DSI_PLL_0P9 pin (or VDDA_DSI{0,1}_PLL_0P9 for sm8150)
+
+  phy-type:
+    description: D-PHY (default) or C-PHY mode
+    enum: [ 10, 11 ]
+    default: 10
+
+required:
+  - compatible
+  - reg
+  - reg-names
+  - vdds-supply
+
+unevaluatedProperties: false
+
+examples:
+  - |
+     #include <dt-bindings/clock/qcom,dispcc-sm8250.h>
+     #include <dt-bindings/clock/qcom,rpmh.h>
+
+     dsi-phy@ae94400 {
+         compatible = "qcom,dsi-phy-7nm";
+         reg = <0x0ae94400 0x200>,
+               <0x0ae94600 0x280>,
+               <0x0ae94900 0x260>;
+         reg-names = "dsi_phy",
+                     "dsi_phy_lane",
+                     "dsi_pll";
+
+         #clock-cells = <1>;
+         #phy-cells = <0>;
+
+         vdds-supply = <&vreg_l5a_0p88>;
+         clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+                  <&rpmhcc RPMH_CXO_CLK>;
+         clock-names = "iface", "ref";
+     };
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index dc7f3e40850b..e9c6af78b1d7 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -116,9 +116,9 @@ config DRM_MSM_DSI_10NM_PHY
 	  Choose this option if DSI PHY on SDM845 is used on the platform.
 
 config DRM_MSM_DSI_7NM_PHY
-	bool "Enable DSI 7nm PHY driver in MSM DRM (used by SM8150/SM8250)"
+	bool "Enable DSI 7nm PHY driver in MSM DRM"
 	depends on DRM_MSM_DSI
 	default y
 	help
-	  Choose this option if DSI PHY on SM8150/SM8250 is used on the
-	  platform.
+	  Choose this option if DSI PHY on SM8150/SM8250/SC7280 is used on
+	  the platform.
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 0a93ed1d6b06..5e2750eb3810 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -18,6 +18,18 @@ static void a5xx_dump(struct msm_gpu *gpu);
 
 #define GPU_PAS_ID 13
 
+static void update_shadow_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
+
+	if (a5xx_gpu->has_whereami) {
+		OUT_PKT7(ring, CP_WHERE_AM_I, 2);
+		OUT_RING(ring, lower_32_bits(shadowptr(a5xx_gpu, ring)));
+		OUT_RING(ring, upper_32_bits(shadowptr(a5xx_gpu, ring)));
+	}
+}
+
 void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 		bool sync)
 {
@@ -30,11 +42,8 @@ void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 	 * Most flush operations need to issue a WHERE_AM_I opcode to sync up
 	 * the rptr shadow
 	 */
-	if (a5xx_gpu->has_whereami && sync) {
-		OUT_PKT7(ring, CP_WHERE_AM_I, 2);
-		OUT_RING(ring, lower_32_bits(shadowptr(a5xx_gpu, ring)));
-		OUT_RING(ring, upper_32_bits(shadowptr(a5xx_gpu, ring)));
-	}
+	if (sync)
+		update_shadow_rptr(gpu, ring);
 
 	spin_lock_irqsave(&ring->preempt_lock, flags);
 
@@ -168,6 +177,16 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 			ibs++;
 			break;
 		}
+
+		/*
+		 * Periodically update shadow-wptr if needed, so that we
+		 * can see partial progress of submits with large # of
+		 * cmds.. otherwise we could needlessly stall waiting for
+		 * ringbuffer state, simply due to looking at a shadow
+		 * rptr value that has not been updated
+		 */
+		if ((ibs % 32) == 0)
+			update_shadow_rptr(gpu, ring);
 	}
 
 	/*
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index d7cec7f0dde0..a7c58018959f 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -519,9 +519,9 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 	if (!pdcptr)
 		goto err;
 
-	if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
+	if (adreno_is_a650(adreno_gpu) || adreno_is_a660_family(adreno_gpu))
 		pdc_in_aop = true;
-	else if (adreno_is_a618(adreno_gpu) || adreno_is_a640(adreno_gpu))
+	else if (adreno_is_a618(adreno_gpu) || adreno_is_a640_family(adreno_gpu))
 		pdc_address_offset = 0x30090;
 	else
 		pdc_address_offset = 0x30080;
@@ -933,6 +933,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 
 	/* Use a known rate to bring up the GMU */
 	clk_set_rate(gmu->core_clk, 200000000);
+	clk_set_rate(gmu->hub_clk, 150000000);
 	ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
 	if (ret) {
 		pm_runtime_put(gmu->gxpd);
@@ -1393,6 +1394,9 @@ static int a6xx_gmu_clocks_probe(struct a6xx_gmu *gmu)
 	gmu->core_clk = msm_clk_bulk_get_clock(gmu->clocks,
 		gmu->nr_clocks, "gmu");
 
+	gmu->hub_clk = msm_clk_bulk_get_clock(gmu->clocks,
+		gmu->nr_clocks, "hub");
+
 	return 0;
 }
 
@@ -1504,7 +1508,7 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	 * are otherwise unused by a660.
 	 */
 	gmu->dummy.size = SZ_4K;
-	if (adreno_is_a660(adreno_gpu)) {
+	if (adreno_is_a660_family(adreno_gpu)) {
 		ret = a6xx_gmu_memory_alloc(gmu, &gmu->debug, SZ_4K * 7, 0x60400000);
 		if (ret)
 			goto err_memory;
@@ -1522,7 +1526,7 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 			SZ_16M - SZ_16K, 0x04000);
 		if (ret)
 			goto err_memory;
-	} else if (adreno_is_a640(adreno_gpu)) {
+	} else if (adreno_is_a640_family(adreno_gpu)) {
 		ret = a6xx_gmu_memory_alloc(gmu, &gmu->icache,
 			SZ_256K - SZ_16K, 0x04000);
 		if (ret)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index 71dfa60070cc..3c74f64e3126 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -66,6 +66,7 @@ struct a6xx_gmu {
 	int nr_clocks;
 	struct clk_bulk_data *clocks;
 	struct clk *core_clk;
+	struct clk *hub_clk;
 
 	/* current performance index set externally */
 	int current_perf_index;
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 989301230f14..40c9fef457a4 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -52,21 +52,25 @@ static bool a6xx_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	return true;
 }
 
-static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+static void update_shadow_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
-	uint32_t wptr;
-	unsigned long flags;
 
 	/* Expanded APRIV doesn't need to issue the WHERE_AM_I opcode */
 	if (a6xx_gpu->has_whereami && !adreno_gpu->base.hw_apriv) {
-		struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
-
 		OUT_PKT7(ring, CP_WHERE_AM_I, 2);
 		OUT_RING(ring, lower_32_bits(shadowptr(a6xx_gpu, ring)));
 		OUT_RING(ring, upper_32_bits(shadowptr(a6xx_gpu, ring)));
 	}
+}
+
+static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+{
+	uint32_t wptr;
+	unsigned long flags;
+
+	update_shadow_rptr(gpu, ring);
 
 	spin_lock_irqsave(&ring->preempt_lock, flags);
 
@@ -145,7 +149,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	struct msm_ringbuffer *ring = submit->ring;
-	unsigned int i;
+	unsigned int i, ibs = 0;
 
 	a6xx_set_pagetable(a6xx_gpu, ring, submit->queue->ctx);
 
@@ -181,8 +185,19 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
 			OUT_RING(ring, upper_32_bits(submit->cmd[i].iova));
 			OUT_RING(ring, submit->cmd[i].size);
+			ibs++;
 			break;
 		}
+
+		/*
+		 * Periodically update shadow-wptr if needed, so that we
+		 * can see partial progress of submits with large # of
+		 * cmds.. otherwise we could needlessly stall waiting for
+		 * ringbuffer state, simply due to looking at a shadow
+		 * rptr value that has not been updated
+		 */
+		if ((ibs % 32) == 0)
+			update_shadow_rptr(gpu, ring);
 	}
 
 	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0),
@@ -652,7 +667,7 @@ static void a6xx_set_cp_protect(struct msm_gpu *gpu)
 		regs = a650_protect;
 		count = ARRAY_SIZE(a650_protect);
 		count_max = 48;
-	} else if (adreno_is_a660(adreno_gpu)) {
+	} else if (adreno_is_a660_family(adreno_gpu)) {
 		regs = a660_protect;
 		count = ARRAY_SIZE(a660_protect);
 		count_max = 48;
@@ -683,7 +698,7 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 	if (adreno_is_a618(adreno_gpu))
 		return;
 
-	if (adreno_is_a640(adreno_gpu))
+	if (adreno_is_a640_family(adreno_gpu))
 		amsbc = 1;
 
 	if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu)) {
@@ -694,6 +709,13 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 		uavflagprd_inv = 2;
 	}
 
+	if (adreno_is_7c3(adreno_gpu)) {
+		lower_bit = 1;
+		amsbc = 1;
+		rgb565_predicator = 1;
+		uavflagprd_inv = 2;
+	}
+
 	gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL,
 		rgb565_predicator << 11 | amsbc << 4 | lower_bit << 1);
 	gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, lower_bit << 1);
@@ -740,6 +762,7 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 {
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct msm_gpu *gpu = &adreno_gpu->base;
+	const char *sqe_name = adreno_gpu->info->fw[ADRENO_FW_SQE];
 	u32 *buf = msm_gem_get_vaddr(obj);
 	bool ret = false;
 
@@ -756,8 +779,7 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 	 *
 	 * a660 targets have all the critical security fixes from the start
 	 */
-	if (adreno_is_a618(adreno_gpu) || adreno_is_a630(adreno_gpu) ||
-		adreno_is_a640(adreno_gpu)) {
+	if (!strcmp(sqe_name, "a630_sqe.fw")) {
 		/*
 		 * If the lowest nibble is 0xa that is an indication that this
 		 * microcode has been patched. The actual version is in dword
@@ -778,7 +800,7 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 		DRM_DEV_ERROR(&gpu->pdev->dev,
 			"a630 SQE ucode is too old. Have version %x need at least %x\n",
 			buf[0] & 0xfff, 0x190);
-	} else if (adreno_is_a650(adreno_gpu)) {
+	} else if (!strcmp(sqe_name, "a650_sqe.fw")) {
 		if ((buf[0] & 0xfff) >= 0x095) {
 			ret = true;
 			goto out;
@@ -787,7 +809,7 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 		DRM_DEV_ERROR(&gpu->pdev->dev,
 			"a650 SQE ucode is too old. Have version %x need at least %x\n",
 			buf[0] & 0xfff, 0x095);
-	} else if (adreno_is_a660(adreno_gpu)) {
+	} else if (!strcmp(sqe_name, "a660_sqe.fw")) {
 		ret = true;
 	} else {
 		DRM_DEV_ERROR(&gpu->pdev->dev,
@@ -897,7 +919,8 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	a6xx_set_hwcg(gpu, true);
 
 	/* VBIF/GBIF start*/
-	if (adreno_is_a640(adreno_gpu) || adreno_is_a650_family(adreno_gpu)) {
+	if (adreno_is_a640_family(adreno_gpu) ||
+	    adreno_is_a650_family(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE0, 0x00071620);
 		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE1, 0x00071620);
 		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE2, 0x00071620);
@@ -935,13 +958,14 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A6XX_UCHE_FILTER_CNTL, 0x804);
 	gpu_write(gpu, REG_A6XX_UCHE_CACHE_WAYS, 0x4);
 
-	if (adreno_is_a640(adreno_gpu) || adreno_is_a650_family(adreno_gpu))
+	if (adreno_is_a640_family(adreno_gpu) ||
+	    adreno_is_a650_family(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x02000140);
 	else
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x010000c0);
 	gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_1, 0x8040362c);
 
-	if (adreno_is_a660(adreno_gpu))
+	if (adreno_is_a660_family(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_CP_LPAC_PROG_FIFO_SIZE, 0x00000020);
 
 	/* Setting the mem pool size */
@@ -952,8 +976,10 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	*/
 	if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200);
-	else if (adreno_is_a640(adreno_gpu))
+	else if (adreno_is_a640_family(adreno_gpu) || adreno_is_7c3(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00200200);
+	else if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200);
 	else
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00180000);
 
@@ -990,13 +1016,15 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	/* Protect registers from the CP */
 	a6xx_set_cp_protect(gpu);
 
-	if (adreno_is_a660(adreno_gpu)) {
+	if (adreno_is_a660_family(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_CP_CHICKEN_DBG, 0x1);
 		gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x0);
-		/* Set dualQ + disable afull for A660 GPU but not for A635 */
-		gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG, 0x66906);
 	}
 
+	/* Set dualQ + disable afull for A660 GPU */
+	if (adreno_is_a660(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG, 0x66906);
+
 	/* Enable expanded apriv for targets that support it */
 	if (gpu->hw_apriv) {
 		gpu_write(gpu, REG_A6XX_CP_APRIV_CNTL,
@@ -1383,13 +1411,13 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
 {
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct msm_gpu *gpu = &adreno_gpu->base;
-	u32 cntl1_regval = 0;
+	u32 gpu_scid, cntl1_regval = 0;
 
 	if (IS_ERR(a6xx_gpu->llc_mmio))
 		return;
 
 	if (!llcc_slice_activate(a6xx_gpu->llc_slice)) {
-		u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
+		gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
 
 		gpu_scid &= 0x1f;
 		cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) |
@@ -1409,26 +1437,34 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
 		}
 	}
 
-	if (cntl1_regval) {
+	if (!cntl1_regval)
+		return;
+
+	/*
+	 * Program the slice IDs for the various GPU blocks and GPU MMU
+	 * pagetables
+	 */
+	if (!a6xx_gpu->have_mmu500) {
+		a6xx_llc_write(a6xx_gpu,
+			REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1, cntl1_regval);
+
 		/*
-		 * Program the slice IDs for the various GPU blocks and GPU MMU
-		 * pagetables
+		 * Program cacheability overrides to not allocate cache
+		 * lines on a write miss
 		 */
-		if (a6xx_gpu->have_mmu500)
-			gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, GENMASK(24, 0),
-				cntl1_regval);
-		else {
-			a6xx_llc_write(a6xx_gpu,
-				REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1, cntl1_regval);
-
-			/*
-			 * Program cacheability overrides to not allocate cache
-			 * lines on a write miss
-			 */
-			a6xx_llc_rmw(a6xx_gpu,
-				REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF, 0x03);
-		}
+		a6xx_llc_rmw(a6xx_gpu,
+			REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF, 0x03);
+		return;
 	}
+
+	gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, GENMASK(24, 0), cntl1_regval);
+
+	/* On A660, the SCID programming for UCHE traffic is done in
+	 * A6XX_GBIF_SCACHE_CNTL0[14:10]
+	 */
+	if (adreno_is_a660_family(adreno_gpu))
+		gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL0, (0x1f << 10) |
+			(1 << 8), (gpu_scid << 10) | (1 << 8));
 }
 
 static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu)
@@ -1667,11 +1703,11 @@ static u32 a618_get_speed_bin(u32 fuse)
 	return UINT_MAX;
 }
 
-static u32 fuse_to_supp_hw(struct device *dev, u32 revn, u32 fuse)
+static u32 fuse_to_supp_hw(struct device *dev, struct adreno_rev rev, u32 fuse)
 {
 	u32 val = UINT_MAX;
 
-	if (revn == 618)
+	if (adreno_cmp_rev(ADRENO_REV(6, 1, 8, ANY_ID), rev))
 		val = a618_get_speed_bin(fuse);
 
 	if (val == UINT_MAX) {
@@ -1684,14 +1720,13 @@ static u32 fuse_to_supp_hw(struct device *dev, u32 revn, u32 fuse)
 	return (1 << val);
 }
 
-static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu,
-		u32 revn)
+static int a6xx_set_supported_hw(struct device *dev, struct adreno_rev rev)
 {
 	u32 supp_hw = UINT_MAX;
-	u16 speedbin;
+	u32 speedbin;
 	int ret;
 
-	ret = nvmem_cell_read_u16(dev, "speed_bin", &speedbin);
+	ret = nvmem_cell_read_variable_le_u32(dev, "speed_bin", &speedbin);
 	/*
 	 * -ENOENT means that the platform doesn't support speedbin which is
 	 * fine
@@ -1704,9 +1739,8 @@ static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu,
 			      ret);
 		goto done;
 	}
-	speedbin = le16_to_cpu(speedbin);
 
-	supp_hw = fuse_to_supp_hw(dev, revn, speedbin);
+	supp_hw = fuse_to_supp_hw(dev, rev, speedbin);
 
 done:
 	ret = devm_pm_opp_set_supported_hw(dev, &supp_hw, 1);
@@ -1772,12 +1806,13 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	 */
 	info = adreno_info(config->rev);
 
-	if (info && (info->revn == 650 || info->revn == 660))
+	if (info && (info->revn == 650 || info->revn == 660 ||
+			adreno_cmp_rev(ADRENO_REV(6, 3, 5, ANY_ID), info->rev)))
 		adreno_gpu->base.hw_apriv = true;
 
 	a6xx_llc_slices_init(pdev, a6xx_gpu);
 
-	ret = a6xx_set_supported_hw(&pdev->dev, a6xx_gpu, info->revn);
+	ret = a6xx_set_supported_hw(&pdev->dev, config->rev);
 	if (ret) {
 		a6xx_destroy(&(a6xx_gpu->base.base));
 		return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
index 919433732b43..d4c65bf0a1b7 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
@@ -382,6 +382,36 @@ static void a660_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 	msg->cnoc_cmds_data[1][0] =  0x60000001;
 }
 
+static void adreno_7c3_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
+{
+	/*
+	 * Send a single "off" entry just to get things running
+	 * TODO: bus scaling
+	 */
+	msg->bw_level_num = 1;
+
+	msg->ddr_cmds_num = 3;
+	msg->ddr_wait_bitmask = 0x07;
+
+	msg->ddr_cmds_addrs[0] = 0x50004;
+	msg->ddr_cmds_addrs[1] = 0x50000;
+	msg->ddr_cmds_addrs[2] = 0x50088;
+
+	msg->ddr_cmds_data[0][0] =  0x40000000;
+	msg->ddr_cmds_data[0][1] =  0x40000000;
+	msg->ddr_cmds_data[0][2] =  0x40000000;
+
+	/*
+	 * These are the CX (CNOC) votes - these are used by the GMU but the
+	 * votes are known and fixed for the target
+	 */
+	msg->cnoc_cmds_num = 1;
+	msg->cnoc_wait_bitmask = 0x01;
+
+	msg->cnoc_cmds_addrs[0] = 0x5006c;
+	msg->cnoc_cmds_data[0][0] =  0x40000000;
+	msg->cnoc_cmds_data[1][0] =  0x60000001;
+}
 static void a6xx_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 {
 	/* Send a single "off" entry since the 630 GMU doesn't do bus scaling */
@@ -428,10 +458,12 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
 
 	if (adreno_is_a618(adreno_gpu))
 		a618_build_bw_table(&msg);
-	else if (adreno_is_a640(adreno_gpu))
+	else if (adreno_is_a640_family(adreno_gpu))
 		a640_build_bw_table(&msg);
 	else if (adreno_is_a650(adreno_gpu))
 		a650_build_bw_table(&msg);
+	else if (adreno_is_7c3(adreno_gpu))
+		adreno_7c3_build_bw_table(&msg);
 	else if (adreno_is_a660(adreno_gpu))
 		a660_build_bw_table(&msg);
 	else
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 6dad8015c9a1..2a6ce76656aa 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -8,8 +8,6 @@
 
 #include "adreno_gpu.h"
 
-#define ANY_ID 0xff
-
 bool hang_debug = false;
 MODULE_PARM_DESC(hang_debug, "Dump registers when hang is detected (can be slow!)");